Department of Business Development and Technology

Predicting the Product Life Cycle of Songs on the Radio: How Record Labels Can Manage Product Portfolios and Prioritise Artists by Using Machine Learning Techniques

Research output: Contribution to conferencePaperResearchpeer-review

Standard

Harvard

APA

CBE

MLA

Vancouver

Author

Bibtex

@conference{c7c58ce3427d4988848df4b614d5d7cd,
title = "Predicting the Product Life Cycle of Songs on the Radio: How Record Labels Can Manage Product Portfolios and Prioritise Artists by Using Machine Learning Techniques",
abstract = "Abstract. In terms of determining the success of a musical artist's song, there is a positive correlation of radio play success and music sales success. Therefore, being able to forecast the future plays of a song on the radio can serve as powerful risk management and product portfolio management tools for record labels and other stakeholders of a song. This research strives to predict the remaining product life cycle of a song on the radio after it has been played for one or two months. The best results were achieved using a k-d tree to calculate the songs the most similar to the test songs and use a Random Forest model to forecast radio plays. An 82.78% and 83.44% accuracy was achieved for the two time periods, respectively. This explorative research leads to over 4500 test metrics to find the best combination of models and pre-processing techniques. Other algorithms tested were KNN, MLP, and CNN. The features only consist of daily radio plays and use no musical features.",
keywords = "Hit Song Science, Product Life Cycle, Machine Learning, Radio",
author = "Grooss, {Oliver Fuglsang} and {Nissum Holm}, Claus and Alphinas, {Robert A.}",
year = "2021",
month = jul,
day = "15",
language = "English",

}

RIS

TY - CONF

T1 - Predicting the Product Life Cycle of Songs on the Radio

T2 - How Record Labels Can Manage Product Portfolios and Prioritise Artists by Using Machine Learning Techniques

AU - Grooss, Oliver Fuglsang

AU - Nissum Holm, Claus

AU - Alphinas, Robert A.

PY - 2021/7/15

Y1 - 2021/7/15

N2 - Abstract. In terms of determining the success of a musical artist's song, there is a positive correlation of radio play success and music sales success. Therefore, being able to forecast the future plays of a song on the radio can serve as powerful risk management and product portfolio management tools for record labels and other stakeholders of a song. This research strives to predict the remaining product life cycle of a song on the radio after it has been played for one or two months. The best results were achieved using a k-d tree to calculate the songs the most similar to the test songs and use a Random Forest model to forecast radio plays. An 82.78% and 83.44% accuracy was achieved for the two time periods, respectively. This explorative research leads to over 4500 test metrics to find the best combination of models and pre-processing techniques. Other algorithms tested were KNN, MLP, and CNN. The features only consist of daily radio plays and use no musical features.

AB - Abstract. In terms of determining the success of a musical artist's song, there is a positive correlation of radio play success and music sales success. Therefore, being able to forecast the future plays of a song on the radio can serve as powerful risk management and product portfolio management tools for record labels and other stakeholders of a song. This research strives to predict the remaining product life cycle of a song on the radio after it has been played for one or two months. The best results were achieved using a k-d tree to calculate the songs the most similar to the test songs and use a Random Forest model to forecast radio plays. An 82.78% and 83.44% accuracy was achieved for the two time periods, respectively. This explorative research leads to over 4500 test metrics to find the best combination of models and pre-processing techniques. Other algorithms tested were KNN, MLP, and CNN. The features only consist of daily radio plays and use no musical features.

KW - Hit Song Science

KW - Product Life Cycle

KW - Machine Learning

KW - Radio

M3 - Paper

ER -